def test_tfidf_params(self):
corpus = ['a b c', 'b c d d', 'c b e c f']
ids = ['u1', 'u2', 'u3']
modality = TextModality(corpus=corpus,
ids=ids,
max_vocab=6,
tfidf_params={
'binary': False,
'norm': 'l2',
'use_idf': True,
'smooth_idf': True,
'sublinear_tf': False
}).build({
'u1': 0,
'u2': 1,
'u3': 2
})
npt.assert_array_equal(modality.batch_tfidf([1]),
self.modality.batch_tfidf([1]))
for k, v in {
'binary': True,
'norm': 'l1',
'use_idf': False,
'smooth_idf': False,
'sublinear_tf': True
}.items():
modality = TextModality(corpus=corpus,
ids=ids,
max_vocab=6,
tfidf_params={k: v})
modality.build({'u1': 0, 'u2': 1, 'u3': 2})
self.assertFalse(
np.array_equal(modality.batch_tfidf([1]),
self.modality.batch_tfidf([1])))
def test_batch_bow_fallback(self):
modality = TextModality(features=np.asarray([[3, 2, 1], [4, 5, 6]]),
ids=['a', 'b'])
modality.build()
npt.assert_array_equal(np.asarray([[3, 2, 1]]),
modality.batch_bow(batch_ids=[0]))
class TestTextModality(unittest.TestCase):
def setUp(self):
self.tokens = ['a', 'b', 'c', 'd', 'e', 'f']
corpus = ['a b c', 'b c d d', 'c b e c f']
ids = ['u1', 'u2', 'u3']
# frequency ranking: c > b > d > a > e > f
self.modality = TextModality(corpus=corpus, ids=ids, max_vocab=6)
self.modality.build({'u1': 0, 'u2': 1, 'u3': 2})
self.token_ids = (self.modality.vocab.tok2idx[tok]
for tok in self.tokens)
def test_init(self):
self.assertCountEqual(self.modality.vocab.idx2tok,
SPECIAL_TOKENS + self.tokens)
def test_build(self):
TextModality().build()
TextModality(corpus=['abc']).build()
TextModality(corpus=['abc']).build({'b': 0})
TextModality(corpus=['abc'], ids=['a']).build({'b': 0})
def test_sequences(self):
(a, b, c, d, e, f) = self.token_ids
self.assertListEqual(self.modality.sequences,
[[a, b, c], [b, c, d, d], [c, b, e, c, f]])
def test_batch_seq(self):
(a, b, c, d, e, f) = self.token_ids
batch_seqs = self.modality.batch_seq([2, 1])
self.assertEqual((2, 5), batch_seqs.shape)
npt.assert_array_equal(batch_seqs,
np.asarray([[c, b, e, c, f], [b, c, d, d, 0]]))
batch_seqs = self.modality.batch_seq([0, 2], max_length=4)
self.assertEqual((2, 4), batch_seqs.shape)
npt.assert_array_equal(batch_seqs,
np.asarray([[a, b, c, 0], [c, b, e, c]]))
self.modality.sequences = None
try:
self.modality.batch_seq([0])
except ValueError:
assert True
def test_count_matrix(self):
(a, b, c, d, e, f) = self.token_ids
shift = len(SPECIAL_TOKENS)
expected_counts = np.zeros_like(self.modality.count_matrix.A)
expected_counts[0, a - shift] = 1
expected_counts[0, b - shift] = 1
expected_counts[0, c - shift] = 1
expected_counts[1, b - shift] = 1
expected_counts[1, c - shift] = 1
expected_counts[1, d - shift] = 2
expected_counts[2, b - shift] = 1
expected_counts[2, c - shift] = 2
expected_counts[2, e - shift] = 1
expected_counts[2, f - shift] = 1
npt.assert_array_equal(self.modality.count_matrix.A, expected_counts)
def test_batch_bow(self):
(a, b, c, d, e, f) = self.token_ids
shift = len(SPECIAL_TOKENS)
batch_bows = self.modality.batch_bow([2, 1])
self.assertEqual((2, self.modality.max_vocab), batch_bows.shape)
expected_bows = np.zeros_like(batch_bows)
expected_bows[0, b - shift] = 1
expected_bows[0, c - shift] = 2
expected_bows[0, e - shift] = 1
expected_bows[0, f - shift] = 1
expected_bows[1, b - shift] = 1
expected_bows[1, c - shift] = 1
expected_bows[1, d - shift] = 2
npt.assert_array_equal(batch_bows, expected_bows)
batch_bows = self.modality.batch_bow([0, 2],
binary=True,
keep_sparse=True)
self.assertEqual((2, 6), batch_bows.shape)
expected_bows = np.zeros_like(batch_bows.A)
expected_bows[0, np.asarray([a, b, c]) - shift] = 1
expected_bows[1, np.asarray([b, c, e, f]) - shift] = 1
npt.assert_array_equal(batch_bows.A, expected_bows)
self.modality.count_matrix = None
try:
self.modality.batch_bow([0])
except ValueError:
assert True
def test_batch_bow_fallback(self):
modality = TextModality(features=np.asarray([[3, 2, 1], [4, 5, 6]]),
ids=['a', 'b'])
modality.build()
npt.assert_array_equal(np.asarray([[3, 2, 1]]),
modality.batch_bow(batch_ids=[0]))